Reject Task

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility and does well: it discloses the file move across lifecycle directories, the appended `reject_task` transition event, the non-destructive nature, and the v2 no-op behavior. It does not mention permission prerequisites or failure behavior, but the core side effects are clearly surfaced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core state transition and stays compact. There is minor redundancy between the first and second sentences, but every behavioral point earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, return-value documentation is unnecessary. The description covers lifecycle semantics, exact file paths, event logging, non-destructive intent, and version compatibility, leaving only minor gaps around error cases and permission enforcement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, and the description adds little param-specific meaning. It implies the ADMIN actor role by describing the ADMIN recall mechanism, but the individual parameters `task_id`, `actor`, and `note` are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb pair (reject/recall), the exact target resource (task under review), and the state transition `review → active`. The file-path move and v3 lifecycle context make it clearly distinct from siblings like approve_task, archive_task, or submit_task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context: ADMIN sends work back for revision without discarding it, and the task returns to active for rework. Also provides an explicit exclusion by noting it is a no-op on v2 projects, though it does not name alternative tools or conditionally compare them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.